Intelligent financial time series forecasting: A complex neuro-fuzzy approach with multi-swarm intelligence

Financial investors often face an urgent need to predict the future. Accurate forecasting may allow investors to be aware of changes in financial markets in the future, so that they can reduce the risk of investment. In this paper, we present an intelligent computing paradigm, called the Complex Neuro-Fuzzy System (CNFS), applied to the problem of financial time series forecasting. The CNFS is an adaptive system, which is designed using Complex Fuzzy Sets (CFSs) whose membership functions are complex-valued and characterized within the unit disc of the complex plane. The application of CFSs to the CNFS can augment the adaptive capability of nonlinear functional mapping, which is valuable for nonlinear forecasting. Moreover, to optimize the CNFS for accurate forecasting, we devised a new hybrid learning method, called the HMSPSO-RLSE, which integrates in a hybrid way the so-called Hierarchical Multi-Swarm PSO (HMSPSO) and the wellknown Recursive Least Squares Estimator (RLSE). Three examples of financial time series are used to test the proposed approach, whose experimental results outperform those of other methods.

[1]  Chunshien Li,et al.  Complex fuzzy model with PSO-RLSE hybrid learning approach to function approximation , 2011, Int. J. Intell. Inf. Database Syst..

[2]  Bogdan Trawinski,et al.  Selection of Heterogeneous Fuzzy Model Ensembles Using Self-adaptive Genetic Algorithms , 2011, New Generation Computing.

[3]  Abraham Kandel,et al.  Complex fuzzy sets , 2002, IEEE Trans. Fuzzy Syst..

[4]  James S. Albus,et al.  Data Storage in the Cerebellar Model Articulation Controller (CMAC) , 1975 .

[5]  Nikola K. Kasabov,et al.  HyFIS: adaptive neuro-fuzzy inference systems and their application to nonlinear dynamical systems , 1999, Neural Networks.

[6]  Abraham Kandel,et al.  Complex fuzzy logic , 2003, IEEE Trans. Fuzzy Syst..

[7]  Q. Henry Wu,et al.  MCPSO: A multi-swarm cooperative particle swarm optimizer , 2007, Appl. Math. Comput..

[8]  Jyh-Shing Roger Jang,et al.  ANFIS: adaptive-network-based fuzzy inference system , 1993, IEEE Trans. Syst. Man Cybern..

[9]  Meng Joo Er,et al.  NARMAX time series model prediction: feedforward and recurrent fuzzy neural network approaches , 2005, Fuzzy Sets Syst..

[10]  Quang Tran,et al.  Robust Visual Tracking Using Randomized Forest and Online Appearance Model , 2011, ACIIDS.

[11]  Fakhri Karray,et al.  Inferring operating rules for reservoir operations using fuzzy regression and ANFIS , 2007, Fuzzy Sets Syst..

[12]  Chunshien Li,et al.  Fuzzy control of unknown multiple-input-multiple-output plants , 1999, Fuzzy Sets Syst..

[13]  James Kennedy,et al.  Particle swarm optimization , 2002, Proceedings of ICNN'95 - International Conference on Neural Networks.

[14]  Chunshien Li,et al.  Pseudoerror-based self-organizing neuro-fuzzy system , 2004, IEEE Trans. Fuzzy Syst..

[15]  A. Kandel,et al.  Linguistic coordinate transformations for complex fuzzy sets , 1999, FUZZ-IEEE'99. 1999 IEEE International Fuzzy Systems. Conference Proceedings (Cat. No.99CH36315).

[16]  Krzysztof Siminski,et al.  Rule weights in a neuro-fuzzy system with a hierarchical domain partition , 2010, Int. J. Appl. Math. Comput. Sci..

[17]  Kai-Yuan Cai,et al.  Operation Properties and δ-Equalities of Complex Fuzzy Sets , 2011 .

[18]  S. Dick,et al.  Towards Inductive Learning of Complex Fuzzy Inference Systems , 2007, NAFIPS 2007 - 2007 Annual Meeting of the North American Fuzzy Information Processing Society.

[19]  Kurt Hornik,et al.  Multilayer feedforward networks are universal approximators , 1989, Neural Networks.

[20]  Russell C. Eberhart,et al.  A new optimizer using particle swarm theory , 1995, MHS'95. Proceedings of the Sixth International Symposium on Micro Machine and Human Science.

[21]  S.F. Mekhamer,et al.  A Modified Particle Swarm Optimizer for the Coordination of Directional Overcurrent Relays , 2007, IEEE Transactions on Power Delivery.

[22]  Chunshien Li,et al.  Complex neuro-fuzzy intelligent approach to function approximation , 2010, Third International Workshop on Advanced Computational Intelligence.

[23]  Chunshien Li,et al.  Function Approximation with Complex Neuro-Fuzzy System Using Complex Fuzzy Sets – A New Approach , 2011, New Generation Computing.

[24]  Chunshien Li,et al.  Complex Fuzzy Computing to Time Series Prediction A Multi-Swarm PSO Learning Approach , 2011, ACIIDS.

[25]  Satish Kumar,et al.  Subsethood-product fuzzy neural inference system (SuPFuNIS) , 2002, IEEE Trans. Neural Networks.

[26]  J. Buckley.  Fuzzy complex numbers , 1989 .

[27]  Mietek A. Brdys,et al.  Adaptive Prediction of Stock Exchange Indices by State Space Wavelet Networks , 2009, Int. J. Appl. Math. Comput. Sci..

[28]  Chunshien Li,et al.  Intelligent Forecasting of S&P 500 Time Series - A Self-organizing Fuzzy Approach , 2011, ACIIDS.

[29]  John Moody,et al.  Fast Learning in Networks of Locally-Tuned Processing Units , 1989, Neural Computation.

[30]  R. Priemer,et al.  SELF-LEARNING GENERAL PURPOSE PID CONTROLLER , 1997 .

[31]  Tharam S. Dillon,et al.  Operation properties and delta-equalities of complex fuzzy sets , 2009, Int. J. Approx. Reason..

[32]  Scott Dick,et al.  ANCFIS: A Neurofuzzy Architecture Employing Complex Fuzzy Sets , 2011, IEEE Transactions on Fuzzy Systems.

[33]  Witold Pedrycz,et al.  Fuzzy prediction architecture using recurrent neural networks , 2009, Neurocomputing.

[34]  Mehdi Khashei,et al.  A novel hybridization of artificial neural networks and ARIMA models for time series forecasting , 2011, Appl. Soft Comput..

[35]  Chih-Chou Chiu,et al.  Financial time series forecasting using independent component analysis and support vector regression , 2009, Decis. Support Syst..

[36]  Xingsheng Deng,et al.  Incremental learning of dynamic fuzzy neural networks for accurate system modeling , 2009, Fuzzy Sets Syst..

[37]  Héctor Pomares,et al.  Soft-computing techniques and ARMA model for time series prediction , 2008, Neurocomputing.

[38]  Scott Dick,et al.  Toward complex fuzzy logic , 2005, IEEE Transactions on Fuzzy Systems.

[39]  R. Eberhart,et al.  Fuzzy adaptive particle swarm optimization , 2001, Proceedings of the 2001 Congress on Evolutionary Computation (IEEE Cat. No.01TH8546).

[40]  Hiok Chai Quek,et al.  Financial volatility trading using a self-organising neural-fuzzy semantic network and option straddle-based approach , 2010, Expert Systems with Applications.

[41]  Derya Avci,et al.  An Adaptive Network-Based Fuzzy Inference System (ANFIS) for the prediction of stock market return: The case of the Istanbul Stock Exchange , 2010, Expert Syst. Appl..

[42]  Chunshien Li,et al.  Self-organizing neuro-fuzzy system for control of unknown plants , 2003, IEEE Trans. Fuzzy Syst..

[43]  Juan Luis Castro,et al.  Fuzzy logic controllers are universal approximators , 1995, IEEE Trans. Syst. Man Cybern..